The Technical Program Manager for Inference acts as a bridge between inference systems and the broader organization. This role involves driving strategic initiatives across inference runtime and accelerator performance. The individual will coordinate model launches, manage cross-platform dependencies, and ensure reliability across multiple hardware targets. Responsibilities include leading cross-functional infrastructure integration, identifying optimization opportunities, and prioritizing the inference deployment roadmap. The role also requires building strong relationships across research, engineering, and product teams to ensure alignment on priorities.

Candidates must have several years of experience in technical program management with a proven track record of delivering complex infrastructure programs, specifically in ML/AI or large-scale distributed systems. A deep technical understanding of inference systems, compilers, or hardware accelerators is required to engage with engineering teams. The role requires a minimum of a bachelor's degree or an equivalent combination of education, training, and experience in a relevant field. Strong stakeholder management skills and the ability to create structure in ambiguous environments are essential.